© Neuronpedia 2026
    Privacy & TermsBlogGitHubSlackTwitterContact
    Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    Natural Language
    Autoencoders
    NEW    Assistant AxisNEWCircuit TracerUPDATESteerSAE EvalsExportsAPI Community BlogPrivacy & TermsContact
    1. Home
    3. Joseph Bloom · Feature Splitting for GPT2-Small
    5. GPT2-Small
    7. Residual Feature Splitting 24576
    9. 8-RES_FS24576-JB
    11. 11882
    Prev
    Next
    INDEX
    Explanations

    keywords related to government officials and political activities, specifically related to U.S. lawmakers

    oai_token-act-pair · gpt-3.5-turboTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GPT2-SMALL @ 8-res_fs24576-jb
    Configuration
    jbloom/GPT2-Small-Feature-Splitting-Experiment-Layer-8/blocks.8.hook_resid_pre_24576
    Prompts (Dashboard)
    24,576 prompts, 128 tokens each
    Dataset (Dashboard)
    Skylion007/openwebtext
    Features
    24,576
    Data Type
    torch.float32
    Hook Point
    blocks.8.hook_resid_pre
    Architecture
    standard
    Context Size
    128
    Dataset
    Skylion007/openwebtext
    Hook Point Layer
    8
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Neuron Alignment
    Index
    Value
    % of L₁
    447
    +0.18
    0.8%
    224
    +0.12
    0.5%
    282
    +0.11
    0.5%
    Correlated Neurons
    Index
    P. Corr.
    Cos Sim.
    224
    +0.18
    0.04
    282
    +0.12
    0.04
    488
    +0.11
    0.03
    Negative Logits
    ãĤ¨ãĥ«
    -0.70
    istic
    -0.69
    OUS
    -0.67
    omorph
    -0.67
    Course
    -0.67
    Company
    -0.67
     Fountain
    -0.66
     conquest
    -0.65
    Tur
    -0.64
     Palest
    -0.64
    POSITIVE LOGITS
    hips
    1.29
    hip
    1.18
    ervatives
    1.01
     tasked
    0.94
     voted
    0.92
     unanimously
    0.90
    woman
    0.86
     who
    0.86
    arians
    0.86
     committees
    0.83
    Activations Density 0.071%

    No Known Activations